A Retrospective Evaluation of Energy‐Efficient Object Detection Solutions on Embedded Devices
Ying Wanga, Zhenyu Quanb, Jiajun Li, Yinhe Hanc, Huawei Lid and Xiaowei Lie
State Key Laboratory of Computer Architecture, Institute of Computing Technology Chinese Academy of Sciences, Beijing, P.R. China
a wangying2009@ict.ac.cn
bzlei@ict.ac.cn
cyinhes@ict.ac.cn
dlihuawei@ict.ac.cn
elxw@ict.ac.cn
ABSTRACT
The field of image and video recognition has been propelled by the rapid development of deep learning in recent years. With its fascinating accuracy and generalization ability, deep CNNs have shown remarkable performance in large-scale and real‐life image dataset. However, accommodating computation‐intensive CNN‐based image detection frameworks on power‐constrained devices is considered more challenging than desktop or warehouse computing systems. Instead of emphasizing purely on detection accuracy, Low Power Image Recognition Challenge (LPIRC) is initiated to highlight the energy‐efficiency of different image recognition solutions, and it witnesses the advancement of cost‐effective image recognition technology in aspects of both algorithmic and architecture innovation. This paper introduces the cost‐effective CNN‐based object detection solutions that reached an improved tradeoff between energy and accuracy for mobile CPU+GPU SoCs, which is the winner of LPIRC2016, and it also analyzes the implications of both recent hardware and algorithm advancement on such a technique. It is demonstrated in our evaluation that the performance growth of embedded SoCs and CNN models have clearly contributed to a sheer growth of mAP/WH in current CNN‐based object detection solutions, and also shifted the balance between accuracy and energy‐cost in the contest solution design when we seek to maximize the efficiency score defined by LPIRC through design parameter exploration.
Keywords: Image Recognition, CNN, Energy, GPU.
